© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48407
    Prev
    Next
    INDEX
    Explanations

    nobility and aristocracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įæģ¯
    -0.07
     Engines
    -0.07
    ankind
    -0.07
    irut
    -0.07
    ä¸ĸçķĮ第ä¸Ģ
    -0.07
    ussions
    -0.07
    ibes
    -0.07
     teammates
    -0.07
    ä½ľä¸ºä¸Ģ款
    -0.07
    æĺ¯äººä½ĵ
    -0.07
    POSITIVE LOGITS
    éĺ¶å±Ĥ
    0.14
    éĺ¶
    0.11
    åŃIJå¼Ł
    0.10
    éĺ¶çº§çļĦ
    0.10
    éļİ
    0.09
    éĺ¶çº§
    0.09
     elite
    0.09
    ç²¾èĭ±
    0.09
     elites
    0.09
    è´µæĹı
    0.08
    Activations Density 0.065%

    No Known Activations